© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 265
    Prev
    Next
    INDEX
    Explanations

    4th semesters

    np_acts-logits-general · gemini-2.5-flash-lite

    word endings and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LANA
    0.42
    宻
    0.40
     Lista
    0.39
     iż
    0.39
     ఇప్పటికే
    0.39
    後の
    0.38
    پلز
    0.38
     Alemania
    0.38
    كو
    0.38
     después
    0.37
    POSITIVE LOGITS
    ។
    0.55
    umb
    0.54
    cek
    0.51
    omb
    0.49
    ümü
    0.49
    wik
    0.49
    berg
    0.49
    üll
    0.48
    etric
    0.46
    nec
    0.46
    Activations Density 0.000%

    No Known Activations